logo Idiap Research Institute        
 [BibTeX] [Marc21]
End-to-end Accented Speech Recognition
Type of publication: Idiap-RR
Citation: Viglino_Idiap-RR-04-2022
Number: Idiap-RR-04-2022
Year: 2022
Month: 3
Institution: Idiap
Address: Rue Marconi 19, Martigny
Abstract: Correct pronunciation is known to be the most difficult part to acquire for (native or non-native) language learners. The accented speech is thus more variable, and standard Automatic Speech Recognition (ASR) training approaches that rely on intermediate phone alignment might introduce errors during the ASR training. With end-to-end training we could alleviate this problem. In this work, we explore the use of multi-task training and accent embedding in the context of end-to-end ASR trained with the connectionist temporal classification loss. Comparing to the baseline developed using conventional ASR framework exploiting time-delay neural networks trained on accented English, we show significant relative improvement of about 25% in word error rate. Additional evaluation on unseen accent data yields relative improvements of of 31% and 2% for New Zealand English and Indian English, respectively.
Keywords: accent em- bedding, Accented speech, end-to-end, multi-task, speech recognition
Projects Idiap
Authors Viglino, Thibault
Motlicek, Petr
Cernak, Milos
Crossref by Viglino_INTERSPEECH_2019
Added by: [ADM]
Total mark: 0
Attachments
  • Viglino_Idiap-RR-04-2022.pdf (MD5: 235c152d163b39efe4df4060b7414840)
Notes